A Comparison of Machine Learning Approaches for Prediction of Permeability using Well Log Data in the Hydrocarbon Reservoirs

Abstract

Permeability is a vital parameter in reservoir engineering that affects production directly. Since this parameter's significance is obvious, finding a way for accurate determination of permeability is essential as well. In this paper, the permeability of two notable carbonate reservoirs (Ilam and Sarvak) in the southwest of Iran was predicted by several different methods, and the level of accuracy in all models was compared. For this purpose, Multi-Layer Perceptron Neural Network (MLP), Radial Basis Function Neural Network (RBF), Support Vector Regression (SVR), decision tree (DT), and random forest (RF) methods were chosen. The full set of real well-logging data was investigated by random forest, and five of them were selected as the potent variables. Depth, Computed gamma-ray log (CGR), Spectral gamma-ray log (SGR), Neutron porosity log (NPHI), and density log (RHOB) were considered efficacious variables and used as input data, while permeability was considered output. It should be noted that permeability values are derived from core analysis. Statistical parameters like the coefficient of determination ( ), root mean square error (RMSE) and standard deviation (SD) were determined for the train, test, and total sets. Based on statistical and graphical results, the SVM and DT models perform more accurately than others. RMSE, SD and R2values of SVM and DT models are 0.38, 1.63, 0.97 and 0.44, 2.89, and 0.96 respectively. The results of the best-proposed models of this paper were then compared with the outcome of the empirical equation for permeability prediction. The comparison indicates that artificial intelligence methods perform more accurately than traditional methods for permeability estimation, such as proposed equations. Doi: 10.28991/HEF-2021-02-02-01 Full Text: PDF

Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms

“…Common machine learning methods can be categorized as simple machine learning (SMLM) and hybrid machine learning (HMLM) methods. Focusing on SMLMs, researchers have used artificial neural networks (ANNs) in the form of multilayer perceptron (MLP) and radial basis function (RBF) (Ali and Chawathé 2000;Jamialahmadi and Javadpour 2000;Handhel 2009;Verma et al 2012;Adeniran et al 2019;Okon et al 2020), deep learning (Zhong et al 2019;Kamrava et al 2020;Tian et al 2020;Tang et al 2022), fuzzy neural networks (Ahmadi et al 2014;Elkatatny et al 2018;Adeniran et al 2019), extreme learning machine (ELM) (Sitouah et al 2014;Lin et al 2015), support vector machine (SVM) and least squares SVM (LSSVM) Ahmadi et al 2014;Adeniran et al 2019;Mahdaviara et al 2020a), group method of data handling (Mathew Nkurlu et al 2020;Kamali et al 2022;Mulashani et al 2022), random forest (RF) (Talebkeikhah et al 2021), decision tree (Sitouah et al 2014;Otchere et al 2021;Talebkeikhah et al 2021), and a variety f regression methods such as Gaussian process and multivariate linear regression (Gholami et al 2014;Kamali et al 2022). When it comes to HMLMs, metaheuristic optimization algorithms have been used to determine hyperparameters of estimator algorithms in the process of training the models.…”

Optimizing acidizing design and effectiveness assessment with machine learning for predicting post-acidizing permeability

“…Thus, prior to feeding data into a machine learning algorithm, data cleaning and preprocessing procedures are performed to ensure optimal data quality 39 . Data cleaning encompasses the identification and handling of missing values, outliers, and irrelevant or redundant features 28,37 . Preprocessing procedures involve transforming the data into a format that the machine learning algorithm can comprehend, which may include scaling or normalizing the data to ensure that all features are on a similar scale 38 www.nature.com/scientificreports/ between 0 and 1 or − 1 and 1.…”

Multi-region machine learning-based novel ensemble approaches for predicting COVID-19 pandemic in Africa

“…The ML algorithms are able to read and modify its structure based on a set of observed data with adaptation done by optimizing over a cost function or an objective (Jebara 2012). ML models including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) have already shown prediction potentials in several field of studies including solar radiation (Nourani et al 2019a) dew point temperature (Naganna et al 2019), pan evaporation (Abdullahi and Tahsin 2020), reference evapotranspiration (Nourani et al 2020), statistical downscaling (Elkiran et al 2021), performance measurement of residential buildings (Mohammed et al 2021), soils suitability in airfield applications (Sujatha et al 2021), permeability prediction for hydrocarbon reservoirs (Talebkeikhah et al 2021) to mention a few. However, in terms of outbreak prediction, the ML models have been considered as computing techniques with great potentials.…”